© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 42257
    Prev
    Next
    INDEX
    Explanations

    terms related to software applications and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    gated
    Context Size
    1,024
    Dataset
    Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¤ëĭ¤
    -0.18
    was
    -0.16
    Was
    -0.15
    íķĺëĭ¤
    -0.14
    ugins
    -0.14
    Īëĭ¤
    -0.14
    unga
    -0.14
    ýv
    -0.14
    relude
    -0.14
    .utility
    -0.13
    POSITIVE LOGITS
     are
    0.60
     both
    0.51
     were
    0.49
     alike
    0.47
     aren
    0.45
    both
    0.43
     respectively
    0.42
     BOTH
    0.39
     weren
    0.38
     Both
    0.37
    Activations Density 0.306%

    No Known Activations